"""Specialist inference service — CPU-first NER, classification, and extraction.

Provides batch endpoints for entity extraction, event classification,
relation extraction, and structured fact extraction. Uses GLiNER2 Large
as the initial model candidate with a mock fallback for testing.

Endpoints:
    POST /api/specialist/entities  — batch entity extraction
    POST /api/specialist/classify  — batch event classification
    POST /api/specialist/relations — batch relation extraction
    POST /api/specialist/extract   — batch structured extraction
"""